It is shown that hallucinations often accumulate over long contexts, through self-reinforcing dialogue history, and models are particularly vulnerable to questions requiring premise rejection or refusal, which highlights CEDI as a step toward realistic, systematic, and ecologically valid assessments of MLLMs'capabiliti...
Yijiang Li, Huiqi Zou, Bingyang Wang et al.· arXiv.org· 0 citations
Self-Supervised Visual On-Policy Distillation (S$^2$VOPD), a simple yet effective method that constructs on-policy learning signals from asymmetric augmented views, systematically explores a broad design space of visual augmentations and uncover that asymmetry matters.
Yijiang Li, Yijun Liang, Yunjie Tian et al.· 0 citations
U-OPSD first samples multiple rollouts and constructs a pseudo solution by majority vote under a self-consistency threshold, and conditions the model's distribution on the pseudo-solution and distills itself on the disagreeing completions, allowing the model to correct itself precisely where it is confidently wrong.
